--- title: "AI agents for software companies: 15 real examples" canonical: "https://agenticfeats.com/agents-for/software-companies/" receipts: 15 shown: 4 page: 1 pages: 1 --- > From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt # AI agents for software companies Agentic Feats lists 15 sourced examples of AI agents used in software companies; 4 link the artifact; most common agent: Devin (6). The most common job type here is coding. ## Feats, newest first - [One month testing Devin](https://agenticfeats.com/c/one-month-testing-devin.md) (Devin; Numbers; 2026-10-13): Devin was connected to the RunLLM GitHub repo and given small bug fixes and one larger full-stack task over a month. Result: Small scoped fixes took about five minutes to test and merge versus roughly an hour by hand; the full-stack task failed and was rewritten. - [Docs maintenance with Devin](https://agenticfeats.com/c/docs-maintenance-with-devin.md) (Devin; Numbers; 2026-10-13): Devin handled a docs team's recurring work: weekly changelog setup, GitHub issue and PR fixes, a multi-file term rename, and code explanations. Result: Devin found nearly every old term in a docs-wide rename, but the edits still needed 20+ manual commits. - [Mental models framework built with agents](https://agenticfeats.com/c/mental-models-framework-built-with-agents-claude-code.md) (Claude Code, Cursor, Other; Numbers; 2026-10-13): A solo founder gave Claude, ChatGPT, Windsurf, and Cursor defined roles to build and deploy a 120-model mental models framework. Result: The author shipped 120 models, an MCP server for Claude Desktop, and 140 chaos tests with a 100% pass rate over 22 months. - [Devin builds Devin](https://agenticfeats.com/c/devin-builds-devin.md) (Devin; Numbers; 2026-10-13): Devin handles Cognition's own engineering work across Slack, Linear, and the web app: PRs, code review, bug triage, debugging, and design system audits. Result: Cognition merged 659 Devin PRs into its own codebase in one week, up from 154 in its best week of 2025. - [Devin building Devin](https://agenticfeats.com/c/devin-building-devin.md) (Devin; Shown; 2026-10-13): Cognition's team uses Devin across Slack, Linear, web, CLI and API to write, review, triage and debug code in its own codebase. Result: Cognition merged 659 Devin-authored PRs into its own codebase in one week, up from 154 in its best week of 2025. - [Local browser testing loop](https://agenticfeats.com/c/local-browser-testing-loop-claude-code.md) (Claude Code, Claude in Chrome; Claim; 2026-10-13): Claude Code with the Chrome extension builds features, then opens localhost in the author's real Chrome session to test, read console errors, and fix issues. Result: On a dashboard filter task, Claude fixed URL query param handling in three iterations without the author touching the browser. - [Devin cloud testing of PRs](https://agenticfeats.com/c/devin-cloud-testing-of-prs.md) (Devin; Numbers; 2026-10-13): Devin writes a test plan, runs the app on a cloud VM with computer use, and returns annotated test videos and reports. Result: Test runs approved per day on Devin more than doubled in a couple of months, and engineers run 10 to 20 Devins in parallel. - [World Cup reels for app signups](https://agenticfeats.com/c/world-cup-reels-for-app-signups-openclaw.md) (Claude Code, OpenClaw; Shown; 2026-10-13): OpenClaw tracked World Cup results and had Claude post a templated Instagram trial reel after each match. Result: Ben Guez reports over one million views and 200 DMs within a few days, with replies routed to his language app. - [Internal sales AI for Cursor reps](https://agenticfeats.com/c/internal-sales-ai-for-cursor-reps-custom-agent.md) (Custom agent; Numbers; 2026-10-13): Cursor's Head of Enterprise Growth built ChatGTM, an internal chat tool that pulls CRM, call, and web data to draft outreach and research accounts. Result: Used across Cursor's 400+ person sales org, it reportedly helps SDRs book 3x more qualified meetings and cuts AE ramp time by over 50%. - [Engineer bots managing cloud agents](https://agenticfeats.com/c/engineer-bots-managing-cloud-agents-grok-bot.md) (Grok Bot, Other; Numbers; 2026-10-13): A SpaceXSI engineer runs five Grok Bot engineer bots that spin up Cursor cloud agents, review PRs via a Notion database, and auto-merge low-risk changes. Result: The fleet manages over 200 cloud agents at once, up from 15 managed by hand, and built Grok Bot iOS v0 in three weeks. - [Million-line codebase refactor](https://agenticfeats.com/c/million-line-codebase-refactor-hermes-agent.md) (Hermes Agent; Shown; 2026-10-13): Hermes Agent split a million-line Python repo into 36 groups and dispatched 1,393 subagents in git worktrees to refactor it. Result: Non-test Python fell from 1,063,826 to 698,363 lines (34.4%), gateway/run.py from 34,847 to 5,512 lines, and functions over 300 lines from 192 to 2. - [OpenAI build-fix agent on OpenClaw](https://agenticfeats.com/c/openai-build-fix-agent-on-openclaw.md) (OpenClaw; Claim; 2026-10-13): An OpenAI engineer reports an internal OpenClaw agent, Androidclaw, working across Git, GitHub and logs to trace broken builds back to their causes. Result: Androidclaw traces broken builds to the relevant pull request and incident, and sometimes prepares and merges fixes itself. - [Hospital-style agent pipeline ships Db2 support](https://agenticfeats.com/c/hospital-style-agent-pipeline-ships-db2-support-custom-agent.md) (Custom agent; Shown; 2026-10-13): Cockroach Labs ran a multi-role coding agent pipeline modeled on a teaching hospital to add Db2 support to its MOLT migration tool. Result: Db2 support shipped in under two days for a $4172 token bill, versus 9 months and about $160K for Oracle; 27 PRs merged. - [Month of Devin tasks](https://agenticfeats.com/c/month-of-devin-tasks.md) (Devin; Numbers; 2026-10-13): Devin was given more than 20 real coding, research, and code-modification tasks over a month by an Answer.AI team to test its autonomy. Result: Out of 20 tasks, Devin had 14 failures, 3 successes, and 3 inconclusive results, with no pattern predicting which would work. - [Agent workforce for unstaffed functions](https://agenticfeats.com/c/agent-workforce-for-unstaffed-functions-lindy.md) (Lindy; Numbers; 2026-10-13): Ankor's CEO built Lindy agents covering lead research, technical support, content and marketing, and meeting prep, work too small to justify dedicated hires. Result: Ten agents were live in the first week and 20-30 run today. The CEO estimates at least a 5x return on investment.